Parallelisation of Sequential Monte Carlo for real-time control in air traffic management

Eele, Alison; Maciejowski, Jan M.; Chau, Thomas; Luk, Wayne

doi:10.1109/cdc.2013.6760651

Cited by 7 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The real-world aircraft movement information is taken from freely-available data on the website FlightRadar24, following the techniques described in [33,34] (The tools are available at https://github.com/gm-tools/gm-tools). FlightRadar24, which has also been used to gather airborne flight tracks [35,36,37,38], collects automatic dependent surveillance-broadcast (ADS/B) messages transmitted by many aircraft. These messages contain the latitude, longitude and altitude, usually every 5 to 10 seconds.…”

Section: Datamentioning

confidence: 99%

Aircraft taxi time prediction: Feature importance and their implications

Wang

Brownlee

Woodward

et al. 2021

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

Section: Datamentioning

confidence: 99%

Aircraft taxi time prediction: Feature importance and their implications

Wang

Brownlee

Woodward

et al. 2021

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

“…In fact, setting Q = 0 in our method makes the forward pass identical to PF-MPC. The interest in PF-MPC is increasing and it has been applied to, e.g., air traffic management [Eele et al 2013], but it has not been demonstrated with simulated bipeds. The main difference of PF-MPC in contrast to our method is that information is only propagated forward and there is no backward messages or local refinement.…”

Section: Related Workmentioning

confidence: 99%

Online control of simulated humanoids using particle belief propagation

Hämäläinen

Rajamäki

Liu³

2015

ACM Trans. Graph.

View full text Add to dashboard Cite

Figure 1: Our algorithm can handle complex balancing and manipulation tasks while adapting to user interactions. All our demonstrated movements emerge from simple cost functions without animation data or offline precomputation. More examples can be found in the supplemental video and on the project homepage. AbstractWe present a novel, general-purpose Model-Predictive Control (MPC) algorithm that we call Control Particle Belief Propagation (C-PBP). C-PBP combines multimodal, gradient-free sampling and a Markov Random Field factorization to effectively perform simultaneous path finding and smoothing in high-dimensional spaces. We demonstrate the method in online synthesis of interactive and physically valid humanoid movements, including balancing, recovery from both small and extreme disturbances, reaching, balancing on a ball, juggling a ball, and fully steerable locomotion in an environment with obstacles. Such a large repertoire of movements has not been demonstrated before at interactive frame rates, especially considering that all our movement emerges from simple cost functions. Furthermore, we abstain from using any precomputation to train a control policy offline, reference data such as motion capture clips, or state machines that break the movements down into more manageable subtasks. Operating under these conditions enables rapid and convenient iteration when designing the cost functions.

show abstract

“…It has been previously been proposed there is a large degree of speed up that can be obtained by parallelising the SMC algorithm. [16][17][18][19] The authors previous work 20 focused on implementation on a graphics processing unit (GPU) using the CUDA programming language provided by NVIDIA and demonstrated a 98% computational improvement. CUDA is a scalable parallel programming language similar to C and C++ with the libraries and utility to design kernels to implement on a GPU.…”

Section: Parallelisation Implementationmentioning

confidence: 99%

Control of Aircraft in the Terminal Manoeuvring Area using Parallelised Sequential Monte Carlo

Eele

Maciejowski

Chau

et al. 2013

AIAA Guidance, Navigation, and Control (GNC) Conference

Self Cite

View full text Add to dashboard Cite

This paper reports on the use of a parallelised Model Predictive Control, Sequential Monte Carlo algorithm for solving the problem of conflict resolution and aircraft trajectory control in air traffic management specifically around the terminal manoeuvring area of an airport. The target problem is nonlinear, highly constrained, non-convex and uses a single decision-maker with multiple aircraft. The implementation includes a temporal spatio wind model and rolling window simulations for realistic ongoing scenarios. The method is capable of handling both arriving and departing aircraft including some with very low fuel remaining. The aircraft are optimised for multi priority objective functions dependant on whether they are arriving or departing. A novel flow field is proposed to smooth the approach trajectories for arriving aircraft and all trajectories are planned in three dimensions.

show abstract

Parallelisation of Sequential Monte Carlo for real-time control in air traffic management

Cited by 7 publications

References 19 publications

Aircraft taxi time prediction: Feature importance and their implications

Aircraft taxi time prediction: Feature importance and their implications

Online control of simulated humanoids using particle belief propagation

Control of Aircraft in the Terminal Manoeuvring Area using Parallelised Sequential Monte Carlo

Contact Info

Product

Resources

About